{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:2CVWDJBDPH2MUONX4TUHY5AOKK","short_pith_number":"pith:2CVWDJBD","schema_version":"1.0","canonical_sha256":"d0ab61a42379f4ca39b7e4e87c740e52970637ee893d6a2eb46d91a087ec3408","source":{"kind":"arxiv","id":"2607.18589","version":1},"attestation_state":"computed","paper":{"title":"Planning as Emergent Behavior in Reinforcement Learning with Relational Hidden States","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Armin Sommer","submitted_at":"2026-07-20T23:49:42Z","abstract_excerpt":"Reinforcement learning is conventionally divided into model-based and model-free methods. In this taxonomy, model-based methods perform lookahead planning over a learned world model, whereas model-free methods learn a reactive state-action mapping. Recent work, however, has shown that planning can emerge from model-free reinforcement learning alone. The conditions under which this behavior emerges from a pure reward-maximization objective have so far remained unclear. In this paper, we present evidence that, in the observed cases, the hidden-state structure of the neural architecture is the de"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2607.18589","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2026-07-20T23:49:42Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"72a68ca5a5900d8dbd9380ee90570c7bc9ed939e07a21de277bbe13833280025","abstract_canon_sha256":"a7338d26052336917d3d9b94fbde618ea4b8648a3ae3f0ecdd2ba43ff14380d9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-22T00:22:55.599244Z","signature_b64":"LamR+lCdSMF74fwJ4/x7406BZfLBksf7PjB/kTjMQJdjHwdAkxS+x7ipDrrKFZwx+ihp/egFa66HWbG2BGduDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d0ab61a42379f4ca39b7e4e87c740e52970637ee893d6a2eb46d91a087ec3408","last_reissued_at":"2026-07-22T00:22:55.598491Z","signature_status":"signed_v1","first_computed_at":"2026-07-22T00:22:55.598491Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Planning as Emergent Behavior in Reinforcement Learning with Relational Hidden States","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Armin Sommer","submitted_at":"2026-07-20T23:49:42Z","abstract_excerpt":"Reinforcement learning is conventionally divided into model-based and model-free methods. In this taxonomy, model-based methods perform lookahead planning over a learned world model, whereas model-free methods learn a reactive state-action mapping. Recent work, however, has shown that planning can emerge from model-free reinforcement learning alone. The conditions under which this behavior emerges from a pure reward-maximization objective have so far remained unclear. In this paper, we present evidence that, in the observed cases, the hidden-state structure of the neural architecture is the de"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.18589","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2607.18589/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2607.18589","created_at":"2026-07-22T00:22:55.598884+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.18589v1","created_at":"2026-07-22T00:22:55.598884+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.18589","created_at":"2026-07-22T00:22:55.598884+00:00"},{"alias_kind":"pith_short_12","alias_value":"2CVWDJBDPH2M","created_at":"2026-07-22T00:22:55.598884+00:00"},{"alias_kind":"pith_short_16","alias_value":"2CVWDJBDPH2MUONX","created_at":"2026-07-22T00:22:55.598884+00:00"},{"alias_kind":"pith_short_8","alias_value":"2CVWDJBD","created_at":"2026-07-22T00:22:55.598884+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/2CVWDJBDPH2MUONX4TUHY5AOKK","json":"https://pith.science/pith/2CVWDJBDPH2MUONX4TUHY5AOKK.json","graph_json":"https://pith.science/api/pith-number/2CVWDJBDPH2MUONX4TUHY5AOKK/graph.json","events_json":"https://pith.science/api/pith-number/2CVWDJBDPH2MUONX4TUHY5AOKK/events.json","paper":"https://pith.science/paper/2CVWDJBD"},"agent_actions":{"view_html":"https://pith.science/pith/2CVWDJBDPH2MUONX4TUHY5AOKK","download_json":"https://pith.science/pith/2CVWDJBDPH2MUONX4TUHY5AOKK.json","view_paper":"https://pith.science/paper/2CVWDJBD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.18589&json=true","fetch_graph":"https://pith.science/api/pith-number/2CVWDJBDPH2MUONX4TUHY5AOKK/graph.json","fetch_events":"https://pith.science/api/pith-number/2CVWDJBDPH2MUONX4TUHY5AOKK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2CVWDJBDPH2MUONX4TUHY5AOKK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2CVWDJBDPH2MUONX4TUHY5AOKK/action/storage_attestation","attest_author":"https://pith.science/pith/2CVWDJBDPH2MUONX4TUHY5AOKK/action/author_attestation","sign_citation":"https://pith.science/pith/2CVWDJBDPH2MUONX4TUHY5AOKK/action/citation_signature","submit_replication":"https://pith.science/pith/2CVWDJBDPH2MUONX4TUHY5AOKK/action/replication_record"}},"created_at":"2026-07-22T00:22:55.598884+00:00","updated_at":"2026-07-22T00:22:55.598884+00:00"}